Colocating Teleophthalmology Within Primary Care Settings to Improve Access to Diabetic Retinopathy Screening: Retrospective Descriptive Evaluation
Bibliographic record
Abstract
BACKGROUND: Annual retinal exams for patients with diabetes are critical as diabetic retinopathy is the number one cause of preventable blindness in working-age adults in the United States. Currently, most patients with diabetes in the United States receive a referral from their primary care provider to see an ophthalmologist for their annual dilated eye exam, which can be an added inconvenience and expense. As such, there is a need for alternative screening strategies within an outpatient network. The use of a telemedicine platform in a primary care setting serves as a novel strategy to increase diabetic retinopathy screening rates. In order to provide better access to diabetic retinopathy screening for our patients, cameras were placed in 3 primary care practices in October 2017 as part of an 8-month pilot program. Specialized cameras from Intelligent Retinal Imaging Systems (IRIS) were used to acquire images that could be interpreted remotely by ophthalmologists within the LifeBridge Health network for the diagnosis of diabetic retinopathy and the detection of other types of pathology (eg, macular edema). OBJECTIVE: The aim of this retrospective descriptive study was to examine whether a telemedicine platform can be used as a cost-effective way to increase diabetic retinopathy screening rates in the primary care setting. METHODS: Aggregate screening volume and diagnostic data were collected for each of the 3 practice locations for the 8-month pilot period (October 30, 2017, through June 30, 2018). Additionally, payor reimbursement data and equipment cost data were used to determine the payback period for each of the 3 practice locations. RESULTS: The pilot program proved the business case that implementation of the IRIS camera in 3 practice locations could result in enough patients being screened to pay for the cost of the camera within a maximum of 2 years. The 3 practices showed increased diabetic retinopathy screening rates of 1%, 6%, and 24%, respectively, and were all able to screen enough patients to be on track to pay off the cost of the camera within 2 years of implementation. Aggregate data from the pilot period showed that of the 1213 patients who were screened, approximately 17.1% (n=207) were diagnosed with diabetic retinopathy and an additional 17.7% (n=215) were suspected of having some other form of pathology. Of note, 10.1% (n=123) were also identified as being "IRIS saves," defined as having pathology identified that was severe enough to be considered an imminent threat to their vision. CONCLUSIONS: This retrospective descriptive study suggests that a telemedicine platform can be used to improve diabetic retinopathy screening rates in the primary care setting within a large health care system in a cost-effective way that allows for the cost of the equipment to be recouped through billing within a maximum of 2 years.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".